我试图让这段代码正常工作，但是当我尝试对事物进行编码时，它似乎并没有按预期工作。 我有一个60字节的文本文件。我编码它，输出的文件是100字节。当我解码该文件时，它会像65bytes一样。它正确解码但文件大小比原始大。 我尝试编码jpg，文件大小确实下降，但是我无法打开文件。我试图解码jpg文件，它没有工作，似乎cmd冻结了。这是我试图使用的代码。
import java.util.*;
import java.io.*;
public class LZW {
// Dictionary
public static short DSIZE = 256;
public static int DSIZEINT = 256;
/** Compress a string to a list of output symbols. */
public static List<Short> compress(String uncompressed) {
// Build the dictionary.
short dictSize = DSIZE;
Map<String,Short> dictionary = new HashMap<String,Short>();
for (short i = 0; i < DSIZE; i++)
dictionary.put("" + (char)i, i);
String w = "";
List<Short> result = new ArrayList<Short>();
for (char c : uncompressed.toCharArray()) {
String wc = w + c;
if (dictionary.containsKey(wc))
w = wc;
else {
result.add(dictionary.get(w));
// Add wc to the dictionary.
dictionary.put(wc, dictSize++);
w = "" + c;
}
}
// Output the code for w.
if (!w.equals(""))
result.add(dictionary.get(w));
return result;
}
/** Compress a string to a list of output symbols, supporting larger filesizes. */
public static List<Integer> compressInt(String uncompressed) {
// Build the dictionary.
int dictSize = DSIZEINT;
Map<String,Integer> dictionary = new HashMap<String,Integer>();
for (int i = 0; i < DSIZEINT; i++)
dictionary.put("" + (char)i, i);
String w = "";
List<Integer> result = new ArrayList<Integer>();
for (char c : uncompressed.toCharArray()) {
String wc = w + c;
if (dictionary.containsKey(wc))
w = wc;
else {
result.add(dictionary.get(w));
// Add wc to the dictionary.
dictionary.put(wc, dictSize++);
w = "" + c;
}
}
// Output the code for w.
if (!w.equals(""))
result.add(dictionary.get(w));
return result;
}
/** Decompress a list of output ks to a string. */
public static String decompress(List<Short> compressed) {
// Build the dictionary.
short dictSize = DSIZE;
Map<Short,String> dictionary = new HashMap<Short,String>();
for (short i = 0; i < DSIZE; i++)
dictionary.put(i, "" + (char)i);
String w = "" + (char)(short)compressed.remove(0);
String result = w;
for (short k : compressed) {
String entry;
if (dictionary.containsKey(k))
entry = dictionary.get(k);
else if (k == dictSize)
entry = w + w.charAt(0);
else
throw new IllegalArgumentException("Bad compressed k: " + k);
result += entry;
// Add w+entry[0] to the dictionary.
dictionary.put(dictSize++, w + entry.charAt(0));
w = entry;
}
return result;
}
/** Decompress a list of output ks to a string, supporting larger filesizes. */
public static String decompressInt(List<Integer> compressed) {
// Build the dictionary.
int dictSize = DSIZE;
Map<Integer,String> dictionary = new HashMap<Integer,String>();
for (int i = 0; i < DSIZE; i++)
dictionary.put(i, "" + (char)i);
String w = "" + (char)(int)compressed.remove(0);
String result = w;
for (int k : compressed) {
String entry;
if (dictionary.containsKey(k))
entry = dictionary.get(k);
else if (k == dictSize)
entry = w + w.charAt(0);
else
throw new IllegalArgumentException("Bad compressed k: " + k);
result += entry;
// Add w+entry[0] to the dictionary.
dictionary.put(dictSize++, w + entry.charAt(0));
w = entry;
}
return result;
}
public static void main(String[] args) {
String example = "";
String s = "";
int command = 0;
//Check for correct argument
if(args.length != 1) {
System.out.println("Please enter 1 argument.\nArg1: Command ('encode', 'decode', 'encodeInt', 'decodeInt')\nAnd ensure that you are feeding in an input file and output file using '<' and '>'");
System.exit(1);
}
if(args[0].equals("encode")){
command = 1;
}
else if(args[0].equals("decode")){
command = 2;
}
else if(args[0].equals("encodeInt")){
command = 3;
}
else if(args[0].equals("decodeInt")){
command = 4;
}
else {
System.out.println("Please use either 'encode', 'decode', 'encodeInt', 'decodeInt' as the argument.");
System.exit(1);
}
long start;
long elapsedTime;
//Compress
if(command == 1){
//Read input file
s = BinaryStdIn.readString();
//The actual compression
start = System.nanoTime();
List<Short> compressed = compress(s);
elapsedTime = System.nanoTime() - start;
//System.err.println(compressed);
//first writes the number of ints to write
BinaryStdOut.write(compressed.size());
//writes compression (to file)
Iterator<Short> compressIterator = compressed.iterator();
while (compressIterator.hasNext()){
BinaryStdOut.write(compressIterator.next());
}
System.err.println("LZW Encode time: " + elapsedTime + " ns");
}
//Decompress
else if(command == 2){
//Build Integer List with input
List<Short> compressed = new ArrayList<Short>();
int size = BinaryStdIn.readInt();
while(size > 0){
try{
compressed.add(BinaryStdIn.readShort());
}
catch(RuntimeException e){
System.err.print("*");
}
size--;
}
//System.err.println(compressed);
//The actual decompression
start = System.nanoTime();
String decompressed = decompress(compressed);
elapsedTime = System.nanoTime() - start;
//Print out decompressed data (to file)
System.out.println(decompressed);
System.err.println("LZW Decode time: " + elapsedTime + " ns");
}
//Compress using Integer size
else if(command == 3){
//Read input file
s = BinaryStdIn.readString();
//The actual compression
start = System.nanoTime();
List<Integer> compressed = compressInt(s);
elapsedTime = System.nanoTime() - start;
//System.err.println(compressed);
//first writes the number of ints to write
BinaryStdOut.write(compressed.size());
//writes compression (to file)
Iterator<Integer> compressIterator = compressed.iterator();
while (compressIterator.hasNext()){
BinaryStdOut.write(compressIterator.next());
}
System.err.println("LZW Encode time: " + elapsedTime + " ns");
}
//Decompress using Integer size
else if(command == 4){
//Build Integer List with input
List<Integer> compressed = new ArrayList<Integer>();
int size = BinaryStdIn.readInt();
while(size > 0){
try{
compressed.add(BinaryStdIn.readInt());
}
catch(RuntimeException e){
System.err.print("*");
}
size--;
}
//System.err.println(compressed);
//The actual decompression
start = System.nanoTime();
String decompressed = decompressInt(compressed);
elapsedTime = System.nanoTime() - start;
//Print out decompressed data (to file)
System.out.println(decompressed);
System.err.println("LZW Decode time: " + elapsedTime + " ns");
}
BinaryStdOut.close();
}
}
感谢任何帮助。感谢。
答案 0 :(得分：1)
即使是最好的压缩算法也会偶尔创建一个比输入大的输出。事实上，它是一个很好的测试用例来找到这样的输入。 LZW通过查找重复序列进行压缩，因此无任何重复序列的输入必然会变大。
我曾经不得不像这样创建一个测试输入。我认为它类似于＆＃34; ABCD ... ACBDEG ...＆＃34;。
编辑：现在我更仔细地查看代码，我发现你正在为输出编写一个Shorts列表。这几乎肯定是错的;其中一个必要步骤是将每个输出标记打包到最小位数，并且您完全错过了该步骤。
根据您的描述判断代码也存在其他问题，但现在还不够。